A river and lake evaluation scoring method and system

Abstract

The present invention discloses a river and lake evaluation scoring method and system, which relates to the technical field of water body environment evaluation. After selecting monitoring points in a target area, the monitoring points are marked on an electronic map covering the target area; the fluctuation of each monitoring indicator is calculated from the monitoring data, and the target indicator is screened out from the monitoring indicator according to the fluctuation. If the maximum value of the trend coefficient of the target indicator exceeds the expectation, a water body prediction instruction is issued; the target area is divided into several area blocks using a clustering algorithm, and the water body scoring model outputs an evaluation score for each area block, and an evaluation value is constructed from the evaluation score of each area block. Based on the relationship between the evaluation value and the evaluation threshold, an evaluation report is formulated for the target area, or a corresponding river and lake environment improvement plan is output from the lake and river water body environment improvement knowledge map. The multi-dimensional judgment of the water body environment status in the target area is realized, the scoring stability is higher, the coverage is wider, and the obtained evaluation value is more forward-looking.

Description

Technical Field

[0001] The present invention relates to the technical field of water environment evaluation, and in particular to a river and lake evaluation scoring method and system. Background Art

[0002] The environmental scoring of river and lake water bodies usually includes multiple indicators, such as unobstructed flood channels, river water shoreline control, river water body protection, river ecological recovery, etc. Each indicator is further subdivided into more specific evaluation factors, and each evaluation factor is assigned a corresponding score according to certain standards. The scoring is usually based on a variety of methods such as on-site inspections, data verification, supervision and inspection, and daily monitoring. The environmental scoring of river and lake water bodies is a process of comprehensively evaluating the health status of rivers and lakes, which involves multiple indicators and evaluation standards. By quantitatively scoring each indicator, we can understand the health status of rivers and lakes more accurately, and provide strong support for the protection, restoration, development and utilization of rivers and lakes. At the same time, factors such as data accessibility and the scientific nature of the evaluation method also need to be considered in the scoring process.

[0003] In the Chinese invention patent with application publication number CN115713781A, a method and system for evaluating the quality of water ecological environment based on fish monitoring is disclosed. The method provided by the present invention includes: obtaining information of fish in a pre-selected water body area based on echo detection; collecting fish images based on the information of fish; inputting the fish images into a neural network model to identify the species of fish in the fish images; obtaining the total number of fish species in the pre-selected water body area, and obtaining the fish integrity index based on the total number of fish species and the conservative coefficient of the fish species; and judging the water ecological environment quality level of the pre-selected water body area based on the fish integrity index. The present invention can timely, accurately and comprehensively obtain the water ecological environment quality level in the water body area for use in water body ecological environment status evaluation and early warning.

[0004] Combining the above content with the content in the prior art:

[0005] When it is necessary to score the water environment of rivers and lakes and realize a comprehensive evaluation of the water environment of rivers and lakes based on the scores, there are usually many reference standards, such as water quality, ecological conditions and landscape. After completing the data collection of the area to be scored, the scorer compares it with the pre-set standards, obtains the scores of each item, and finally obtains the comprehensive score to complete the evaluation process;

[0006] However, this scoring process mainly involves manual participation, and there are many subjective factors in the scoring. In addition, due to the small long-term fluctuations in the data of some scoring items and the high scoring weights, the overall score does not change much when the water environment has undergone major changes, and the efficiency of water body assessment is not obvious. At the same time, there are certain anomalies in the hydrological state of the water environment. For example, when the water flow is large and the water level rises rapidly, when scoring the river and lake environment under such conditions, there will be a large difference between the output score and the actual score, resulting in insufficient reliability of the given score.

[0007] To this end, the present invention provides a river and lake evaluation and scoring method and system. Summary of the invention

[0008] 1. Technical issues to be resolved

[0009] In view of the deficiencies of the prior art, the present invention provides a river and lake evaluation scoring method and system, which selects target indicators from the monitoring indicators based on the volatility. If the maximum value of the trend coefficient of the target indicator exceeds the expectation, a water body prediction instruction is issued to the outside; a clustering algorithm is used to divide the target area into several regional blocks, and the water body scoring model outputs an evaluation score for each regional block, and an evaluation value is constructed from the evaluation score of each regional block. Based on the relationship between the evaluation value and the evaluation threshold, an evaluation report is formulated for the target area, or a corresponding river and lake environment improvement plan is output from the lake and river water body environment improvement knowledge map. A multi-dimensional judgment of the water body environment status in the target area is achieved, the scoring stability is higher, and the obtained evaluation value is more forward-looking, thereby solving the technical problems raised in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] A river and lake evaluation scoring method includes: monitoring and acquiring hydrological data in a target area at a hydrological observation point, constructing a water body state data set after summarizing, constructing a water body anomaly degree Pup from the water body state data set, and if the water body anomaly degree Pup does not exceed an anomaly threshold, issuing a water quality data collection instruction to the outside;

[0013] Select the corresponding data source for data collection, collect data at the data source and construct a water body scoring reference data set, preset reference standards based on the reference data, select monitoring points in the target area, and mark them on the electronic map covering the target area;

[0014] Collect monitoring data of each monitoring indicator at the monitoring point, calculate the fluctuation of each monitoring indicator from the monitoring data, select the target indicator from the monitoring indicator according to the fluctuation, conduct trend analysis on the target indicator, and construct the trend coefficient Xpa from the obtained analysis data. If the maximum value of the trend coefficient Xpa exceeds the expectation, issue a water body prediction instruction to the outside.

[0015] The water body prediction model is used to predict the water body data. Combined with the predicted data, the target area is divided into several area blocks using the clustering algorithm. The water body scoring model outputs an evaluation score for each area block. The evaluation value Pzg is constructed from the evaluation score of each area block. The corresponding control instructions are issued based on the relationship between the evaluation value Pzg and the evaluation threshold.

[0016] After receiving the control command, an evaluation report is prepared for the target area or the corresponding river and lake environment improvement plan is output from the lake and river water environment improvement knowledge map; after the improvement plan is implemented, the improvement degree Gos in the target area is constructed according to the change of the evaluation value Pzg. If the improvement degree Gos does not exceed the expectation, a plan adjustment instruction is issued to the outside;

[0017] After the improvement plan is executed, the corresponding evaluation value Pzg is obtained in each sub-period, and the improvement degree in the target area is constructed by the evaluation value Pzg, in the following manner:

[0018]

[0019] Weight coefficient, 0≤F1≤1, 0≤F2≤1, and F1+F2=1, Pzg i Pzg is the evaluation value in the i-th sub-period after the improvement plan is implemented in the target area. c is the evaluation value before executing the improvement plan; i=1, 2, ...n, where n is the number of sub-cycles.

[0020] Furthermore, the area covered by the water body to be evaluated is determined as the target area, and hydrological observation points are set in the target area. The hydrological data in the target area are monitored in each sub-period, and the acquired monitoring data are summarized to construct a water body state data set; the water body anomaly degree Pup is constructed from the water body state data set, wherein the water level rise speed Sn and the water body flow Tn are linearly normalized, and the corresponding data values ​​are mapped to the interval [0, 1] according to the following formula:

[0021]

[0022] Among them, α is the weight coefficient, Sn i is the water level rising speed in the ith sub-period, Sn p is the acceptable value of water level rise rate, Hn i is the water flow in the ith sub-period, Hnp is an acceptable value for water flow.

[0023] Furthermore, after receiving the water quality data collection instruction, water body scores and related data are collected; the corresponding data source is selected for data collection, and the collected data is aggregated to construct a water body score reference data set; an electronic map covering the target area is constructed, and monitoring points are set in the target area. The locations of the monitoring points in the target area meet the following constraints;

[0024]

[0025] Where n is the number of monitoring points in the target area, L(i, j) is the distance between the i-th monitoring point and the j-th monitoring point, and L a is the distance average, and Pup is the water body anomaly in the target area.

[0026] Further, a monitoring indicator is selected in the target area, the monitoring indicator is monitored at each monitoring point in the target area, the monitoring value of the monitoring indicator at each node is collected, and the acquired monitoring values ​​are aggregated to construct a monitoring indicator data set;

[0027] The fluctuation degree Eo of each monitoring indicator is calculated from the monitoring value in the monitoring indicator data set, several monitoring indicators are ranked according to the fluctuation degree Eo, and several monitoring indicators with the highest ranking are taken as target indicators.

[0028] Furthermore, the monitored values ​​of the monitoring indicators are linearly normalized, the corresponding data values ​​are mapped to the interval [0, 1], and the volatility Eo is constructed according to the following formula:

[0029]

[0030] Among them, B i is the monitoring value of the monitoring indicator at the i-th node, B a is the target value of the monitoring value, σ is the standard deviation of several monitoring values; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1.

[0031] Furthermore, after continuously monitoring the target indicators, the continuously acquired monitoring data are trend analyzed and analytical data are acquired, and the trend coefficient Xpa is constructed from the acquired analytical data.

[0032] Among them, the difference and slope between two adjacent monitoring data values ​​are obtained, which are used as the trend difference He and trend rate Hf respectively, and both are linearly normalized to map the corresponding data values ​​to the interval [0, 1] according to the following formula:

[0033]

[0034] Weight coefficient: 0≤ζ≤1, i=1, 2,…, k, k is the number of nodes;

[0035] He i is the trend difference of the ith one, He a is the mean of the trend difference, He p is the qualified target value of trend difference, is the variance of the trend difference; Hf i is the ith trend rate, Hf a is the mean of the trend rate, Hf p is the qualified target value of the trend rate, is the variance of the trend rate.

[0036] Furthermore, after receiving the water body prediction instruction, the area radiated by the monitoring point is taken as a sub-area in the target area, so that the target area contains several adjacent sub-areas; the water body data of each sub-area is predicted using the trained water body prediction model, and the prediction data on each prediction node is obtained, and the water body prediction data set is constructed after aggregation;

[0037] Each sub-region is marked with the obtained prediction data, and a clustering algorithm is used to perform cluster analysis on each sub-region and merge similar sub-regions into regional blocks. Each regional block obtained is marked on an electronic map. The water body prediction data in each regional block is used as input, and the trained water body scoring model outputs an evaluation score for each regional block.

[0038] Furthermore, the evaluation value Pzg is constructed for the target area based on the evaluation scores of each area block, wherein the evaluation score Gs of the area block is linearly normalized and the corresponding data value is mapped to the interval [0, 1] according to the following formula:

[0039]

[0040] Weight coefficient, 0≤F1≤1, 0≤F2≤1, and F1+F2=1, Gs i is the evaluation score of the i-th region block, Gs a is the mean value of the evaluation score, i = 1, 2, ... n, n is the number of regional blocks;

[0041] If the obtained evaluation value Pzg exceeds the evaluation threshold, a report preparation instruction is issued to the outside; if the evaluation value does not exceed the evaluation threshold, an improvement instruction is issued to the outside.

[0042] Furthermore, after receiving the formulation instruction, an evaluation report is written based on the data in the target area and the evaluation report is output; after receiving the improvement instruction, feature extraction is performed on the predicted data in the target area to obtain corresponding improvement features; with water body improvement in the target area as the target word, a knowledge graph for improving the environment of lakes and rivers is pre-built, and the knowledge graph for improving the environment of lakes and rivers outputs the corresponding river and lake environment improvement plan for the target area.

[0043] A river and lake evaluation and scoring system includes a hydrological status monitoring unit, which monitors and obtains hydrological data in a target area at a hydrological observation point, constructs a water body status data set after aggregation, constructs a water body anomaly degree Pup from the water body status data set, and sends a water quality data collection instruction to the outside if the water body anomaly degree Pup does not exceed an anomaly threshold;

[0044] The monitoring point selection unit selects the corresponding data source for data collection, collects data at the data source and constructs a water body scoring reference data set, presets reference standards based on the reference data, selects monitoring points in the target area, and marks them on an electronic map covering the target area;

[0045] The water state prediction unit collects monitoring data of various monitoring indicators at the monitoring points, calculates the fluctuation of each monitoring indicator based on the monitoring data, selects the target indicator from the monitoring indicators based on the fluctuation, and constructs the trend coefficient Xpa based on the obtained analysis data after trend analysis. If the maximum value of the trend coefficient Xpa exceeds the expectation, a water body prediction instruction is issued to the outside.

[0046] The scoring evaluation unit uses the water body prediction model to predict the water body data, combines the predicted data, and uses the clustering algorithm to divide the target area into several area blocks. The water body scoring model outputs an evaluation score for each area block, and the evaluation value Pzg is constructed from the evaluation score of each area block. The corresponding control instructions are issued based on the relationship between the evaluation value Pzg and the evaluation threshold;

[0047] After receiving the control command, the emergency processing unit formulates an evaluation report for the target area or outputs the corresponding river and lake environment improvement plan from the knowledge map of lake and river water environment improvement; after executing the improvement plan, it constructs the improvement degree Gos in the target area according to the change of the evaluation value Pzg. If the improvement degree Gos does not exceed the expectation, it issues a plan adjustment instruction to the outside.

[0048] (III) Beneficial effects

[0049] The present invention provides a river and lake evaluation scoring method and system, which has the following beneficial effects:

[0050] 1. If there is a certain change in the hydrological state in the target area, there will be a certain difference between the current score and the actual value when scoring the target area. Scoring the target area when the hydrological state is normal can make the obtained scoring results more reliable and stable.

[0051] 2. Set up monitoring points in the target area, and constrain the position of each monitoring point based on the water body anomaly degree Pup in the target area, so that the distribution of monitoring points in the target area is more reasonable, and the efficiency of data collection is improved when collecting various data in the target area.

[0052] 3. When the changing trend is abnormal, it can be handled in time to avoid abnormal water environment. By constructing the trend coefficient Xpa, the intensity of this trend can be judged, and corresponding processing strategies can be taken according to the size of the trend coefficient Xpa to handle the abnormal water environment in time.

[0053] 4. Calculate the corresponding fluctuation degree Eo based on the fluctuation of the data, and select the target indicator with a larger fluctuation degree from several monitoring indicators based on the fluctuation degree Eo. The effect will be more obvious when it is used to evaluate the water environment.

[0054] 5. Perform cluster analysis on each sub-region. After obtaining several regional blocks, the trained water body scoring model is used to score and obtain the scores of each regional block respectively to complete the preliminary scoring of the water body. By scoring each sub-region separately, the scoring can be more accurate.

[0055] 6. After obtaining the scores of each regional block, the evaluation value Pzg is constructed to complete the scoring of the water environment; based on the various water environment parameters and each regional block, through the comprehensive association of multiple indicators and multiple regions, a multi-dimensional judgment of the water environment status in the target area is achieved. Compared with the scoring based on real-time data and historical data, the scoring is more stable, the coverage is wider, and the obtained evaluation value is more forward-looking.

[0056] 7. Adopt corresponding response strategies for the target area based on the evaluation value Pzg. When the water environment is poor, the knowledge graph for improving the lake and river water environment will output the corresponding river and lake environment improvement plan for the target area. When the water environment is poor, it can quickly output targeted emergency plans to achieve targeted improvement of the water environment.

[0057] 8. Judge whether the current improvement effect has met expectations based on the degree of improvement Gos. If the improvement effect fails to meet expectations, the improvement plan can be adjusted and optimized. This way, when the water environment in the target area is poor and the comprehensive score is low, the water environment can be effectively improved, thereby improving the water environment score in multiple dimensions and with multiple coverage. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic diagram of the process of the river and lake evaluation scoring method of the present invention;

[0059] Figure 2 This is a schematic diagram of the structure of the river and lake evaluation and scoring system of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] See also Figure 1 The present invention provides a river and lake evaluation scoring method, comprising:

[0062] Step 1: Monitor and obtain hydrological data in the target area at the hydrological observation point, construct a water body status data set after aggregation, and construct a water body anomaly degree Pup from the water body status data set. If the water body anomaly degree Pup does not exceed the anomaly threshold, issue a water quality data collection instruction to the outside;

[0063] The step 1 includes the following contents:

[0064] Step 101: determine the area covered by the water body to be evaluated as the target area, set up hydrological observation points in the target area, set up a monitoring period including several sub-periods, monitor the hydrological data in the target area in each sub-period, obtain data such as water level rise speed and water flow, and aggregate the acquired monitoring data to construct a water body state data set;

[0065] Step 102: construct the water body abnormality Pup from the water body state data set, wherein the water level rise rate Sn and the water body flow Tn are linearly normalized, and the corresponding data values ​​are mapped to the interval [0, 1] according to the following formula:

[0066]

[0067] Among them, α is the weight coefficient, and its value falls within [0.05, 0.95], which can be obtained through simulation software analysis or by referring to the hierarchical analysis method; Sn i is the water level rising speed in the ith sub-period, Sn p is the acceptable value of water level rise rate, Hn i is the water flow in the ith sub-period, Hn pis the acceptable value for the water body flow;

[0068] Based on historical data and the expected management of water status in the target area, an abnormal threshold is set in advance; if the acquired water abnormality Pup exceeds the abnormal threshold, it means that the current hydrological status in the target area may be abnormal, and these changes may have a certain impact on the water environment in the target area. For example, the continuous inflow of water from the outside reduces the water quality in the target area. If the water abnormality Pup does not exceed the abnormal threshold, a water quality data collection instruction is issued to the outside;

[0069] When using, combine the contents in steps 101 and 102:

[0070] When it is necessary to assign points and evaluate the water environment in the target area, the changes in the hydrological status are monitored in the target area. If there are certain changes in the hydrological status in the target area, the various water status data in the target area will also change accordingly. If the water body is abnormal, when assigning points to the target area, there will be a certain difference between the current assigned score and the actual value. Therefore, scoring the target area when the hydrological status is normal can make the obtained scoring results more reliable and stable.

[0071] Combining the above content with the content in the prior art:

[0072] When it is necessary to score the water environment of rivers and lakes and realize a comprehensive evaluation of the water environment of rivers and lakes based on the scores, there are usually many reference standards, such as water quality, ecological conditions and landscape. After completing the data collection of the area to be scored, the scorer compares it with the pre-set standards, obtains the scores of each item, and finally obtains the comprehensive score to complete the evaluation process;

[0073] However, this scoring process mainly involves manual participation, and there are many subjective factors in the scoring. In addition, due to the small long-term fluctuations in the data of some scoring items and the high scoring weights, the overall score does not change much when the water environment has undergone major changes, and the efficiency of water body assessment is not obvious. At the same time, there are certain anomalies in the hydrological state of the water environment. For example, when the water flow is large and the water level rises rapidly, when scoring the river and lake environment under such conditions, there will be a large difference between the output score and the actual score, resulting in insufficient reliability of the given score.

[0074] Step 2: Select the corresponding data source for data collection, collect data at the data source and construct a water body scoring reference data set, preset reference standards based on the reference data, select monitoring points in the target area, and mark them on the electronic map covering the target area;

[0075] The step 2 includes the following contents:

[0076] Step 201: After receiving the water quality data collection instruction, collect water body scores and related data; select corresponding data sources for data collection, for example, satellite remote sensing data for monitoring vegetation coverage and water pollution; online monitoring station data for real-time monitoring of water quality parameters, social media data to reflect the public's views on river and lake environments; public data, such as environmental reports, management policies, and other third-party data providers; collect relevant data from various data sources through API interfaces, web crawlers, and data exchange protocols, and aggregate the collected data to construct a water body score reference data set;

[0077] When in use, when it is necessary to assign points within the target area, the data is searched and retrieved, and the retrieved data is used as a reference. The corresponding scoring standards and qualification standards for various parameters can be formulated in advance, so that the output evaluation results are more accurate when assigning points and evaluating.

[0078] Step 202: extracting corresponding scoring standards for each scoring index in the water body scoring reference data set, and matching corresponding qualified target values ​​for each water body monitoring index;

[0079] Construct an electronic map covering the target area, set monitoring points in the target area, and mark the locations of the selected monitoring points on the electronic map; wherein the locations of the monitoring points in the target area meet the following constraints;

[0080]

[0081] Where n is the number of monitoring points in the target area, L(i, j) is the distance between the i-th monitoring point and the j-th monitoring point, and L a is the distance mean, Pup is the water anomaly in the target area;

[0082] When using, combine the contents in steps 201 to 203:

[0083] If it is necessary to collect various data in the target area, monitoring points are set in the target area, and the position of each monitoring point is constrained in combination with the water body anomaly degree Pup in the target area, so that the distribution of monitoring points in the target area is more reasonable, and the efficiency of data collection is improved when collecting various data in the target area.

[0084] Step 3: Collect monitoring data of each monitoring indicator at the monitoring point, calculate the fluctuation of each monitoring indicator from the monitoring data, select the target indicator from the monitoring indicator according to the fluctuation, conduct trend analysis on the target indicator, and construct the trend coefficient Xpa from the obtained analysis data. If the maximum value of the trend coefficient Xpa exceeds the expectation, issue a water body prediction instruction to the outside;

[0085] The step three includes the following contents:

[0086] Step 301: Select monitoring indicators in the target area, including water quality indicators, such as pH value, dissolved oxygen, chemical oxygen demand, etc.; ecological indicators, such as biodiversity, vegetation coverage, etc.; landscape indicators, such as landscape aesthetic value, ecological value, etc.; monitor the monitoring indicators at each monitoring point in the target area, collect the monitoring values ​​of the monitoring indicators at each node, and construct a monitoring indicator data set after summarizing the acquired monitoring values;

[0087] Step 302: Calculate the fluctuation Eo of each monitoring indicator from the monitoring values ​​in the monitoring indicator data set, wherein the monitoring values ​​of the monitoring indicators are linearly normalized and the corresponding data values ​​are mapped to the interval [0, 1] according to the following formula:

[0088]

[0089] Among them, B i is the monitoring value of the monitoring indicator at the i-th node, B a is the target value of the monitoring value, σ is the standard deviation of several monitoring values; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1, the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0090] According to the volatility Eo, several monitoring indicators are ranked, and the top ranked monitoring indicators are used as target indicators, so as to select representative parameters according to the volatility;

[0091] When in use, when more parameters need to be monitored, after collecting several parameters, calculate the corresponding fluctuation degree Eo based on the fluctuation of the data, and select the target indicator with a larger fluctuation degree from several monitoring indicators based on the fluctuation degree Eo. The effect is more obvious when it is used to evaluate the water environment.

[0092] Step 303: After continuously monitoring the target indicator, trend analysis is performed on the continuously acquired monitoring data, for example, exponential smoothing method, autoregressive moving average model and linear trend analysis, and analysis data is obtained, including trend direction, trend strength and trend line, etc.;

[0093] The trend coefficient Xpa is constructed from the acquired analysis data, wherein the difference and slope between two adjacent monitoring data values ​​are obtained, which are respectively used as the trend difference He and the trend rate Hf, and both are linearly normalized to map the corresponding data values ​​to the interval [0, 1] according to the following formula:

[0094]

[0095] Weight coefficient: 0≤ζ≤1, i=1, 2,…, k, k is the number of nodes;

[0096] He i is the trend difference of the ith one, He a is the mean of the trend difference, He p is the qualified target value of trend difference, is the variance of the trend difference; Hf i is the ith trend rate, Hf a is the mean of the trend rate, Hf p is the qualified target value of the trend rate, is the variance of the trend rate.

[0097] If the maximum trend coefficient Xpa in the target indicator exceeds the preset trend threshold, it means that the water state in the current target area may be in a deteriorating state and may need to be dealt with in time. At this time, a water body prediction instruction is issued to the outside;

[0098] When using, combine the contents in steps 301 to 303:

[0099] After the target indicators have been screened out, trend analysis is performed on each target. The change process and status of the target indicators can be obtained based on the trend analysis. When the change trend is abnormal, it can be processed in time. For example, when the hydrological state in the target area is abnormal, resulting in an abnormal water environment, the water environment is avoided. By constructing the trend coefficient Xpa, the intensity of this trend can be judged, so that the corresponding processing strategy can be taken according to the size of the trend coefficient Xpa, and timely processing can be carried out when the water environment is abnormal.

[0100] Step 4: Use the water body prediction model to predict the water body data. Combined with the predicted data, use the clustering algorithm to divide the target area into several area blocks. The water body scoring model outputs an evaluation score for each area block. The evaluation value Pzg is constructed from the evaluation score of each area block. Based on the relationship between the evaluation value Pzg and the evaluation threshold, the corresponding control instruction is issued.

[0101] The step 4 includes the following contents:

[0102] Step 401: after receiving the water body prediction instruction, the area radiated by the monitoring point is taken as a sub-area in the target area, so that the target area contains a number of adjacent sub-areas; the convolutional neural network is trained using the sample data to obtain the trained water body prediction model, the water body data of each sub-area is predicted using the trained water body prediction model, and the prediction data on each prediction node is obtained, such as water quality indicators and ecological indicators, etc., and the water body prediction data set is constructed after aggregation;

[0103] When in use, the various indicator data in the target area are predicted to determine the next change state. At this time, if the state in the water environment is abnormal, it can be processed in advance.

[0104] Step 402: Mark each sub-region respectively with the obtained prediction data, perform cluster analysis on each sub-region using a clustering algorithm and merge similar sub-regions into region blocks, and mark each obtained region block on an electronic map;

[0105] The initial model is constructed by the machine learning algorithm. After the scoring standard is determined, the initial model is trained by the pre-acquired sample data to obtain the trained water body scoring model. The water body prediction data in each area block is used as input, and the trained water body scoring model outputs the evaluation score for each area block.

[0106] When in use, each sub-region is marked with the obtained prediction data, and then cluster analysis is performed on each sub-region. After obtaining several regional blocks, the trained water body scoring model is used to score and obtain the scores of each regional block respectively, completing the preliminary scoring of the water body; by scoring each sub-region separately, the scoring can be more accurate;

[0107] Step 403: construct an evaluation value Pzg for the target area based on the evaluation scores of each area block, and use the evaluation value to score the target area, wherein the evaluation score Gs of the area block is linearly normalized, and the corresponding data value is mapped to the interval [0, 1] according to the following formula:

[0108]

[0109] Weight coefficient, 0≤F1≤1, 0≤F2≤1, and F1+F2=1, Gs i is the evaluation score of the i-th region block, Gs a is the mean value of the evaluation score, i = 1, 2, ... n, n is the number of regional blocks;

[0110] Based on historical data and the expected water management in the target area, the assessment threshold is set in advance; the corresponding control instructions are issued based on the relationship between the assessment value Pzg and the assessment threshold, including:

[0111] If the obtained evaluation value Pzg exceeds the evaluation threshold, it means that the score in the target area is high and can basically meet the preset qualified indicators. At this time, a report preparation instruction is issued to the outside to form evaluation feedback after the scoring and evaluation are completed;

[0112] If the evaluation value does not exceed the evaluation threshold, it means that the various conditions in the target area are poor and need to be dealt with in a targeted manner. At this time, improvement instructions are issued to the outside;

[0113] When used, combine the contents in steps 401 to 403:

[0114] After obtaining the scores of each regional block, an evaluation value Pzg is constructed on this basis to complete the scoring of the water environment; thus, based on each water environment parameter and each regional block, a multi-dimensional judgment of the water environment status in the target area is achieved through the comprehensive association of multiple indicators and multiple regions. Compared with the scoring based on real-time data and historical data, the scoring is more stable, covers a wider range, and the obtained evaluation value is more forward-looking.

[0115] Step 5: After receiving the control command, an evaluation report is prepared for the target area or the corresponding river and lake environment improvement plan is output from the lake and river water environment improvement knowledge map; after the improvement plan is executed, the improvement degree Gos in the target area is constructed according to the change of the evaluation value Pzg. If the improvement degree Gos does not exceed the expectation, a plan adjustment instruction is issued to the outside;

[0116] The step five includes the following contents:

[0117] Step 501: after receiving the formulation instruction, write an evaluation report based on the data in the target area, including evaluation results, existing problems, improvement suggestions, etc., and output the evaluation report;

[0118] After receiving the improvement instruction, feature extraction is performed on each prediction data in the target area to obtain corresponding improvement features;

[0119] Taking water improvement in the target area as the target word, after deep retrieval and entity relationship building, a knowledge graph for lake and river water environment improvement is pre-built. Based on the correspondence between the improvement plan and the knowledge graph for lake and river water environment improvement, the knowledge graph for lake and river water environment improvement outputs the corresponding river and lake environment improvement plan for the target area, including water quality purification, ecological restoration, and landscaping.

[0120] When in use, after obtaining the evaluation value Pzg, a corresponding response strategy is taken for the target area based on the evaluation value Pzg. When the water environment is poor, the lake and river water environment improvement knowledge map outputs the corresponding river and lake environment improvement plan for the target area. When the water environment is poor, targeted emergency plans can be quickly output to achieve targeted improvement of the water environment.

[0121] Step 502: After executing the improvement plan, an observation period including several sub-periods is set, and a corresponding evaluation value Pzg is obtained in each sub-period. The improvement degree in the target area is constructed by the evaluation value Pzg in the following manner:

[0122]

[0123] Weight coefficient, 0≤F1≤1, 0≤F2≤1, and F1+F2=1, the weight coefficient value is the same as the previous value; Pzg i Pzg is the evaluation value in the i-th sub-period after the improvement plan is implemented in the target area. c is the evaluation value before the improvement plan is implemented; i = 1, 2, ... n, n is the number of sub-periods;

[0124] Pre-set improvement thresholds based on historical data and management expectations for water improvements in the target area;

[0125] If the improvement degree Gos does not exceed the improvement threshold, it means that the current improvement plan has not achieved the expected effect when it is executed, and a plan adjustment instruction is issued to the outside. After receiving the plan adjustment instruction, the current improvement plan is adjusted to achieve better results when improving the water environment in the target area.

[0126] When using, combine the contents in steps 501 and 502:

[0127] After completing the scoring of the water environment and achieving targeted treatment of the water environment, the evaluation values ​​before and after the implementation of the plan are collected, and the improvement degree Gos is constructed based on the changes in the evaluation values. Based on the improvement degree Gos, it is judged whether the current improvement effect has met expectations. If the improvement effect fails to meet expectations, the improvement plan can be adjusted and optimized. In this way, when the water environment in the target area is poor and the comprehensive score is low, the water environment can be effectively improved, and the water environment score can be improved in multiple dimensions and with multiple coverage.

[0128] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0129] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0130] The construction method of the knowledge graph for improving the lake and river water environment can refer to the following:

[0131] Data collection and preprocessing: Data collection: Collect a large amount of relevant data on the improvement of lake and river water environment, including but not limited to hydrology, water environment, water ecology, water resources, water safety monitoring data, business data, remote sensing data, basic geographic information data and video data, etc. Preprocessing: Clean, label and preprocess the collected data to remove noise and redundant information to ensure data quality and consistency.

[0132] Entity and relationship identification: Entity identification: Extract entities related to the improvement of lake and river water environment from text data, such as rivers, lakes, pollution sources, and governance technologies. Relationship identification: Analyze the relationship between entities, such as "River A is affected by pollution source B", "Governance technology C is suitable for improving the water quality of River A", etc.

[0133] Knowledge graph construction and storage: Construction: Using graph database technology (such as Neo4j), entities and relationships are stored in the form of nodes and edges to form a knowledge graph. Storage: Define attributes and labels for nodes and edges for subsequent knowledge retrieval and reasoning.

[0134] Update and maintenance of the knowledge graph: Update: As new data and information are added, the knowledge graph is updated regularly to ensure its timeliness and accuracy; Maintenance: The knowledge graph is managed and maintained to ensure its stability and availability.

[0135] See also Figure 2 The present invention provides a river and lake evaluation and scoring system, comprising:

[0136] The hydrological status monitoring unit monitors and obtains the hydrological data in the target area at the hydrological observation point, constructs a water body status data set after aggregation, and constructs a water body anomaly degree Pup from the water body status data set. If the water body anomaly degree Pup does not exceed the anomaly threshold, a water quality data collection instruction is issued to the outside;

[0137] The monitoring point selection unit selects the corresponding data source for data collection, collects data at the data source and constructs a water body scoring reference data set, presets reference standards based on the reference data, selects monitoring points in the target area, and marks them on an electronic map covering the target area;

[0138] The water state prediction unit collects monitoring data of various monitoring indicators at the monitoring points, calculates the fluctuation of each monitoring indicator based on the monitoring data, selects the target indicator from the monitoring indicators based on the fluctuation, and constructs the trend coefficient Xpa based on the obtained analysis data after trend analysis. If the maximum value of the trend coefficient Xpa exceeds the expectation, a water body prediction instruction is issued to the outside.

[0139] The scoring evaluation unit uses the water body prediction model to predict the water body data, combines the predicted data, and uses the clustering algorithm to divide the target area into several area blocks. The water body scoring model outputs an evaluation score for each area block, and the evaluation value Pzg is constructed from the evaluation score of each area block. The corresponding control instructions are issued based on the relationship between the evaluation value Pzg and the evaluation threshold;

[0140] After receiving the control command, the emergency processing unit formulates an evaluation report for the target area or outputs the corresponding river and lake environment improvement plan from the knowledge map of lake and river water environment improvement; after executing the improvement plan, it constructs the improvement degree Gos in the target area according to the change of the evaluation value Pzg. If the improvement degree Gos does not exceed the expectation, it issues a plan adjustment instruction to the outside.

[0141] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0142] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0143] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0144] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only for some logical functions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0148] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A river and lake evaluation scoring method, characterized by: include, The hydrological data in the target area are monitored at the hydrological observation points, and a water body status data set is constructed after aggregation. The water body anomaly degree is constructed from the water body status data set. If the water body is abnormal If the abnormal threshold is not exceeded, a water quality data collection instruction is issued to the outside; Select the corresponding data source for data collection, collect data at the data source and construct a water body scoring reference data set, preset reference standards based on the reference data, select monitoring points in the target area, and mark them on the electronic map covering the target area; Collect monitoring data of each monitoring indicator at the monitoring point, and calculate the fluctuation degree of each monitoring indicator from the monitoring data , according to the volatility Filter out target indicators from the monitoring indicators, perform trend analysis on the target indicators, and construct trend coefficients based on the acquired analysis data. , if the trend coefficient The maximum value exceeds the expectation, and the water body prediction instruction is issued to the outside; The water body prediction model is used to predict the water body data. Combined with the predicted data, the target area is divided into several regional blocks using the clustering algorithm. The water body scoring model outputs an evaluation score for each regional block, and the evaluation value is constructed from the evaluation score of each regional block. , by the evaluation value Relationship with the evaluation threshold, issuing corresponding control instructions; After receiving the control command, an evaluation report is prepared for the target area or the corresponding river and lake environment improvement plan is output from the lake and river water environment improvement knowledge map; after the improvement plan is implemented, the evaluation value is used to The change in the target area creates an improvement in If the improvement If the plan does not exceed expectations, external instructions for adjusting the plan will be issued; Among them, after implementing the improvement plan, the corresponding evaluation value is obtained in each sub-period , by the evaluation value Improvement in the target area , as follows: Weight coefficient, , ,and , is the evaluation value in the i-th sub-period after the improvement plan is implemented in the target area, This is the evaluation value before implementing the improvement plan. , is the number of sub-periods.

2. A river and lake evaluation scoring method according to claim 1, characterized in that: The area covered by the water body to be evaluated is determined as the target area, and hydrological observation points are set up in the target area. The hydrological data in the target area are monitored in each sub-period, and the acquired monitoring data are aggregated to construct a water body status data set; Constructing water body anomaly degree from water body state data set , where the water level rise rate and water flow Perform linear normalization and map the corresponding data values ​​to the interval According to the following formula: in, is the weight coefficient, is the water level rising speed in the ith sub-period, is the acceptable value of water level rise rate, is the water flow in the ith sub-period, is an acceptable value for water flow.

3. A river and lake evaluation scoring method according to claim 2, characterized in that: After receiving the water quality data collection instruction, water body scores and related data are collected; the corresponding data source is selected for data collection, and the collected data is aggregated to construct a water body score reference data set; Construct an electronic map covering the target area and set monitoring points in the target area. The locations of the monitoring points in the target area meet the following constraints. Where q is the number of monitoring points in the target area, is the distance between the lth monitoring point and the jth monitoring point, is the average distance, is the water abnormality in the target area.

4. A river and lake evaluation scoring method according to claim 3, characterized in that: Select monitoring indicators in the target area, monitor the monitoring indicators at each monitoring point in the target area, collect monitoring values ​​of the monitoring indicators at each node, and aggregate the acquired monitoring values ​​to construct a monitoring indicator data set; Calculate the volatility of each monitoring indicator from the monitoring values ​​in the monitoring indicator data set , according to the volatility Several monitoring indicators are ranked, and the top ranked monitoring indicators are used as target indicators.

5. A river and lake evaluation scoring method according to claim 4, characterized in that: Perform linear normalization on the monitored values ​​of the monitoring indicators and map the corresponding data values ​​to the interval The volatility is constructed according to the following formula : in, is the monitoring value of the monitoring indicator at the wth node, is the target value of the monitoring value, is the standard deviation of several monitoring values; weight coefficient: , ,and .

6. A river and lake evaluation scoring method according to claim 5, characterized in that: After continuous monitoring of the target indicators, trend analysis is performed on the continuously acquired monitoring data and analytical data is obtained, and the trend coefficient is constructed from the acquired analytical data. ; The difference and slope between two adjacent monitoring data values ​​are obtained and used as trend difference and slope. and trend rate , perform linear normalization on both and map the corresponding data values ​​to the interval According to the following formula: Weight coefficient: , , is the number of nodes; For the A bad trend, is the mean of the trend difference, is the qualified target value of trend difference, is the variance of the trend difference; For the The trend rate, is the mean of the trend rate, is the qualified target value of the trend rate, is the variance of the trend rate.

7. A river and lake evaluation scoring method according to claim 6, characterized in that: After receiving the water body prediction instruction, the area radiated by the monitoring point in the target area is taken as a sub-area, so that the target area contains several adjacent sub-areas; the water body data of each sub-area is predicted using the trained water body prediction model, and the prediction data on each prediction node is obtained, and the water body prediction data set is constructed after aggregation; Each sub-region is marked with the obtained prediction data, and a clustering algorithm is used to perform cluster analysis on each sub-region and merge similar sub-regions into regional blocks. Each regional block obtained is marked on an electronic map. The water body prediction data in each regional block is used as input, and the trained water body scoring model outputs an evaluation score for each regional block.

8. A river and lake evaluation scoring method according to claim 7, characterized in that: The evaluation value is constructed by dividing the evaluation of each area block into the target area , where the evaluation of the regional blocks is Perform linear normalization and map the corresponding data values ​​to the interval According to the following formula: Weight coefficient, , ,and , For the The evaluation score of each area block is is the mean evaluation score, , is the number of regional blocks; If the evaluation value obtained If the evaluation value exceeds the evaluation threshold, a report formulation instruction will be issued to the outside; if the evaluation value does not exceed the evaluation threshold, an improvement instruction will be issued to the outside.

9. A river and lake evaluation scoring method according to claim 8, characterized in that: After receiving the formulation instruction, write an evaluation report based on the data in the target area and output the evaluation report; after receiving the improvement instruction, extract the features of the predicted data in the target area and obtain the corresponding improvement features; Taking water body improvement in the target area as the target word, a knowledge graph for lake and river water body environment improvement is built in advance, and the lake and river water body environment improvement knowledge graph outputs the corresponding river and lake environment improvement plan for the target area.

10. A river and lake evaluation and scoring system, characterized by: include, The hydrological status monitoring unit monitors and obtains the hydrological data in the target area at the hydrological observation point, constructs a water body status data set after aggregation, and constructs a water body anomaly degree from the water body status data set If the water body is abnormal If the abnormal threshold is not exceeded, a water quality data collection instruction is issued to the outside; The monitoring point selection unit selects the corresponding data source for data collection, collects data at the data source and constructs a water body scoring reference data set, presets reference standards based on the reference data, selects monitoring points in the target area, and marks them on an electronic map covering the target area; The water body state prediction unit collects monitoring data of various monitoring indicators at the monitoring points, calculates the fluctuation of each monitoring indicator based on the monitoring data, selects the target indicator from the monitoring indicators based on the fluctuation, performs trend analysis on the target indicator, and constructs the trend coefficient based on the obtained analysis data. , if the trend coefficient The maximum value exceeds the expectation, and the water body prediction instruction is issued to the outside; The scoring evaluation unit uses the water body prediction model to predict the water body data. Combined with the predicted data, the target area is divided into several area blocks using a clustering algorithm. The water body scoring model outputs an evaluation score for each area block, and the evaluation value is constructed from the evaluation score of each area block. , by the evaluation value Relationship with the evaluation threshold, issuing corresponding control instructions; After receiving the control command, the emergency processing unit formulates an evaluation report for the target area or outputs the corresponding river and lake environment improvement plan from the lake and river water environment improvement knowledge map; after implementing the improvement plan, according to the evaluation value The change in the target area creates an improvement in If the improvement If the plan does not exceed expectations, external instructions for adjusting the plan will be issued.

Images